# =========================================================
# invoicegenerators.in — robots.txt
# Goal: maximum discoverability across search engines, AI
# assistants, referral crawlers and legitimate research bots.
# =========================================================

# ---- Default: allow everything except sensitive paths ----
User-agent: *
Allow: /
Disallow: /api/
Disallow: /includes/
Disallow: /uploads/
Disallow: /config.php
Disallow: /functions.php
Disallow: /database.sql
Disallow: /*.sql$
Disallow: /*.env$

# ---- Sitemaps ----
Sitemap: https://invoicegenerators.in/sitemap.xml

# =========================================================
# AI / LLM training & retrieval crawlers — explicit ALLOW
# (so that our content shows up in ChatGPT, Claude, Gemini,
# Perplexity, and other conversational search products)
# =========================================================

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Bingbot
Allow: /

User-agent: bingbot
Allow: /

User-agent: MSNBot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: MojeekBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: PetalBot
Allow: /

# =========================================================
# Aggressive commercial crawlers — slowed down
# =========================================================
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

User-agent: DotBot
Crawl-delay: 10

User-agent: BLEXBot
Crawl-delay: 10